All Issue

2026 Vol.42, Issue 4 Preview Page
Deep Learning-Based Displacement Prediction of Caisson-Type Quay Walls Using Recorded Earthquake Motions

실제 지진파를 이용한 케이슨 안벽의 딥러닝 기반 변위 예측

Hyeonsu Yun1
,
Seong-Kyu Yun2
,
Jiseong Kim3
,
Gichun Kang4*
윤 현수1
,
윤 성규2
,
김 지성3
,
강 기천4*
1Member, Ph.D Candidate, Department of Civil Engineering, College of Engineering, Gyeongsang National Univ.
2Member, Ph.D, Department of Civil Engineering, College of Engineering, Gyeongsang National Univ.
3Member, Assistant Prof., Department of Land Information and Construction, Vision College of Jeonju
4Member, Associate Prof., Department of Civil Engineering, College of Engineering, Gyeongsang National Univ.
1정회원, 경상국립대학교 토목공학과 박사과정
2정회원, 경상국립대학교 토목공학과 공학박사
3정회원, 전주비전대학교 지적토목학과 조교수
4정회원, 경상국립대학교 토목공학과 부교수
*Corresponding Author
31 August 2026. pp. 263-272
PDF XML Citation
Abstract

Following the 2017 Pohang Earthquake, interest in liquefaction phenomena has increased in Korea, leading to numerous studies on the seismic behavior of structures found on liquefiable ground. In recent years, deep learning approaches based on time-series data have also gained increasing attention, highlighting the need for reliable training datasets covering a wide range of conditions. However, obtaining datasets through physical model tests and field monitoring requires considerable time and expense, while collecting data under diverse ground and structural conditions remains challenging. To address these limitations, this study generated numerical analysis datasets under various input conditions using an effective stress analysis method. Seven recorded earthquake motions were selected as input ground motions, and their acceleration amplitudes were scaled according to return periods of 500, 2,400, and 4,800 years. Parametric analyses were additionally performed by varying the SPT N-value and caisson height to account for variations in ground and structural conditions. Using the resulting datasets, displacement predictions were conducted with two recurrent neural network architectures, namely, gated recurrent unit and long short-term memory models. Both models achieved coefficients of determination (R2) exceeding 0.9, demonstrating high predictive accuracy.

Keywords
Deep learning
Caisson-type quay wall
Earthquake
Liquefaction

국내에서는 포항지진 이후 액상화 현상에 관한 관심이 증가함에 따라, 액상화 지반에서의 구조물 거동을 예측하기 위한 다양한 연구가 수행되고 있다. 최근에는 시계열 데이터를 활용한 딥러닝 연구 또한 활발히 수행되고 있으며, 이를 위한 학습 데이터 구축의 중요성 또한 증가하고 있다. 그러나 모형실험 및 실제 계측 데이터를 활용한 연구는 많은 시간과 비용이 요구되며, 다양한 조건에 대한 데이터를 확보하는 데 한계가 있다. 이에 본 연구에서는 유효응력해석 기법을 활용하여 다양한 입력조건에 대한 수치해석 데이터를 구축하였다. 입력 지진파는 총 7종을 적용하였으며, 500년, 2400년, 4800년 재현주기 수준에 따라 입력 가속도를 조정하였다. 또한 지반 및 구조 조건의 영향을 고려하기 위하여 N치와 케이슨 높이 조건을 변화시켜 해석을 수행하였다. 구축된 데이터를 기반으로 GRU 및 LSTM 알고리즘을 적용한 딥러닝 예측을 수행한 결과, 두 모델 모두 결정계수(R2)가 0.9 이상으로 나타나 전반적으로 우수한 예측 성능을 보였다.

References
1

Bray, J. D. and Sancio, R. B. (2006), “Assessment of the Lique- faction Susceptibility of Fine-Grained Soils”, Journal of Geotechnical and Geoenvironmental Engineering, Vol.132, No.9, pp.1165-1177, https://doi.org/10.1061/(ASCE)1090-0241(2006)132:9(1165).

10.1061/(ASCE)1090-0241(2006)132:9(1165)
2

Han, S.-J., Choo, Y. W., Yoon, S., Han, S.-H., and Kim, J.-E. (2025), “Study on Deep Learning-Based Image Analysis for Structural Vibration in Dynamic Centrifuge Modeling”, Journal of the Korean Geotechnical Society, Vol.41, No.4, pp.53-64, https://doi.org/10.7843/kgs.2025.41.4.53.

10.7843/kgs.2025.41.4.53
3

Hong, S., Kwak, T.-Y., Woo, S.-I., and Kim, S.-R. (2024), “Com- parison of Deep Learning and Measurement-Based Methods for Settlement Prediction in Soft Ground”, Journal of the Korean Geotechnical Society, Vol.40, No.6, pp.67-78, https://doi.org/10.7843/kgs.2024.40.6.67.

10.7843/kgs.2024.40.6.67
4

Iai, S., Matsunaga, T., and Kameoka, T. (1992a), “Strain Space Plasticity Model for Cyclic Mobility”, Soils and Foundations, Vol.32, No.2, pp.1-15.

10.3208/sandf1972.32.2_1
5

Iai, S., Matsunaga, T., and Kameoka, T. (1992b), “Analysis of Undrained Cyclic behavior of Sand under Anisotropic Consolidation”, Soils and Foundations, Vol.32, No.2, pp.16-20.

10.3208/sandf1972.32.2_16
6

Kang, G.-C., Tobita, T., and Iai, S. (2014), “Seismic Simulation of Liquefaction-Induced Uplift Behavior of a Hollow Cylinder Structure Buried in Shallow Ground”, Soil Dynamics and Earthquake Engineering, Vol.64, pp.85-94, https://doi.org/10.1016/j.soildyn.2014.05.006.

10.1016/j.soildyn.2014.05.006
7

Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P. T. P. (2017), “On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima”, Proceedings of the International Conference on Learning Representations (ICLR), https://doi.org/10.48550/arXiv.1609.04836.

10.48550/arXiv.1609.04836
8

Kim, S., Hwang, W.-K., Kim, T.-H., and Kang, G.-C. (2019), “A Case Study on Earthquake-induced Deformation of Quay Wall and Backfill in Pohang by 2D-Effective Stress Analysis”, Journal of the Korean Geotechnical Society, Vol.35, No.7, pp.15-27, https://doi.org/10.7843/kgs.2019.35.7.15.

10.7843/kgs.2019.35.7.15
9

Kim, Y.-J., Ko, K.-W., Kim, B.-M., Park, D.-H., Kim, K.-S., Han, J.-T., and Kim, D.-S. (2020), “Evaluation of Liquefaction Triggering for the Pohang Area Based on SPT and CPT Tests”, Journal of the Korean Geotechnical Society, Vol.36, No.10, pp.57-71, https://doi.org/10.7843/kgs.2020.36.10.57.

10.7843/kgs.2020.36.10.57
10

Sahare, A., Choi, G.-C., and Ueda, K. (2024), “Role of Initial Static Shear on the Cyclic Response of Saturated Backfill Retained by a Sheet-Pile Wall: Insights from the Strain Space Multiple Mechanism Model”, Soil Dynamics and Earthquake Engineering, Vol.179, Article 108542. https://doi.org/10.1016/j.soildyn.2024.108542.

10.1016/j.soildyn.2024.108542
11

Seed, H. B. and Idriss, I. M. (1971), “Simplified Procedure for Evaluating Soil Liquefaction Potential”, Journal of the Soil Mechanics and Foundations Division, ASCE, Vol.97, No.9, pp.1249-1273, https://doi.org/10.1061/JSFEAQ.0001662.

10.1061/JSFEAQ.0001662
12

Smith, S. L. and Le, Q. V. (2018), “A Bayesian Perspective on Generalization and Stochastic Gradient Descent”, Proceedings of the International Conference on Learning Representations (ICLR), https://doi.org/10.48550/arXiv.1710.06451.

10.48550/arXiv.1710.06451
13

Tokimatsu, K. and Seed, H. B. (1987), “Evaluation of Settlements in Sands due to Earthquake Shaking”, Journal of Geotechnical Engineering, ASCE, Vol.113, No.8, pp.861-878, https://doi.org/10.1061/(ASCE)0733-9410(1987)113:8(861).

10.1061/(ASCE)0733-9410(1987)113:8(861)
14

Yun, H., Back, M., Sun, J., Yun, S.-K., and Kang, G. (2024), “A Simplified Method for Evaluating Damage of Caisson-Type Quay Wall During Earthquakes”, Journal of the Korean Geosynthetics Society, Vol.23, No.3, pp.1-14, https://doi.org/10.12814/jkgss.2024.23.3.001.

10.12814/jkgss.2024.23.3.001
15

Yun, H., Yun, S.-K., Kim, J., and Kang, G. (2026b), “Analysis of the Effects of Training Conditions on Deep Learning-Based Prediction of Liquefaction-Induced Damage to Caisson-Type Quay Walls”, Journal of the Korean Geotechnical Society, Vol.42, No.3, pp.113-124, https://doi.org/10.7843/kgs.2026.42.3.113.

10.7843/kgs.2026.42.3.113
16

Yun, H., Yun, S.-K., Lee, S., and Kang, G. (2026a), “Prediction of Settlement of Caisson-type Quay Walls Using Deep Learning During Earthquakes”, Journal of the Korean Geotechnical Society, Vol.42, No.2, pp.89-99, https://doi.org/10.7843/kgs.2026.42.2.89.

10.7843/kgs.2026.42.2.89
17

Yun, S.K, Kim, S.J., Kim, J.S., and Kang, G-C. (2021), “Dynamic behavior of Quay Walls According to N-values of Backfill and Amplitude of Seismic Accelerations”, J. Korean Soc. Hazard Mitig., Vol.21, No.1, pp.207-217, https://doi.org/10.9798/KOSHAM.2021.21.1.207.

10.9798/KOSHAM.2021.21.1.207
Information
  • Publisher :The Korean Geotechnical Society
  • Publisher(Ko) :한국지반공학회
  • Journal Title :Journal of the Korean Geotechnical Society
  • Journal Title(Ko) :한국지반공학회 논문집
  • Volume : 42
  • No :4
  • Pages :263-272
  • Received Date : 2026-08-07
  • Revised Date : 2026-08-24
  • Accepted Date : 2026-08-25
  • DOI :https://doi.org/10.7843/kgs.2026.42.4.263
Journal Informaiton Journal of the Korean Geotechnical Society Journal of the Korean Geotechnical Society
Archives
: Vol.23~28 (2007~2012)
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close